Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/GRCEngClub/claude-grc-engineeringnpx agentmods add commands/grcengclub/claude-grc-engineering/control-checkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/grcengclub/claude-grc-engineering/control-check)<a href="https://agentmods.dev/commands/grcengclub/claude-grc-engineering/control-check"><img src="https://agentmods.dev/badge/commands/grcengclub/claude-grc-engineering/control-check.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.04331 |
| Opus 5 | $0.00005 | $0.02166 |
| Sonnet 5 | $0.00002 | $0.00866 |
| Haiku 4.5 | $0.00001 | $0.00433 |
Grade A, and why
control-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 529 lines · 9 tokens per session scan A 26dc9737e0a2
control-check is a command published in the GitHub repository GRCEngClub/claude-grc-engineering (396 stars, last pushed yesterday), with no licence file. It adds 9 tokens to every session and 4,331 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
report
Produce executive and technical compliance reports.
evidence
Collect, hash, and package audit artifacts for assessors.
remediate
Draft actionable remediation for open audit findings.
scope
Define the audit boundary before any control testing.
audit
Execute framework-specific control tests against scoped systems.
assess
Full SAIL V2 gap analysis of the AI agent/system in the current repo — component inventory, all 91 catalog risks dispositioned, prioritized recommendations. Writes SAIL-assessment.md.